Object detection is the latest technology which is used to identify objects and instances of objects in ana image or a video. It is the computer vision technique which is useful in determining the instances of objects in the image and also to identify their locations. The advantage of this technique is that it gives accurate location of the objects and also helps to label them in the image. Object detection contributes a lot in major fields like crowd detection at a particular place, self-driving cars, helps to identify theft by video surveillance etc. Object detection is also used to identify the face recognition, pedestrian recognition which ensures safety on road, also used in image retrieval etc. There are many models which are used in object detection process to simplify the process and gives accurate and efficient results. This paper will discuss the various approaches which are used along with object detection process to enhance the quality of results it will provide.

The outbreak of the Corona Virus (COVID-19) that has begun in December 2019 drastically affected the world. Endemic Coronavirus (COVID-19) is rapidly growing across the globe. SARS-CoV-2 is the virus name that causes a highly contagious and deadly disease COVID-19. It also entered India by the end of January 2020 and has significantly influenced India. More than two million people worldwide have been confirmed to have been contaminated with this virus as of the date (29 July 2020), and more than 7, 24,000 have died of this disease. The governments of most countries, including India, have already taken several measures to reduce the spread of COVID-19, such as lockdown, social distancing, closure of shopping malls, gyms, schools, universities, religious gatherings, etc. This lockdown has affected every Indian sector, such as the Economy, Retail Sector, Tourism Industry, etc. This paper aims to explore to what extent a 2020 epidemic like Covid-19 had impacted the Indian economy using a machine learning approach. The statistical data from esteemed and trustworthy information sources were gathered to realize the impact of the Corona Virus on the Indian economy. Based on this trusted data, analysis has been performed using the various regression models.

No abstract

Neural machine translation (NMT) is an ongoing technique used to implement machine translation (MT) systems. Natural language processing (NLP) researchers have shown that NMT systems are unable to deal with out-of-vocabulary (OOV) words and multi-word expressions (MWEs) in the text. OOV words are those that are not part of the current vocabulary of the NMT system. MWEs are phrases that consist of a minimum of two terms but are treated as a single unit. MWEs have great importance in NLP, linguistic theory, and MT systems. In this article, OOV words and MWEs are handled for the Punjabi to English NMT system. A parallel corpus for Punjabi to English containing MWEs was developed and used to train the different models of NMT. Punjabi is a low-resource language as it lacks the availability of a large parallel corpus for building various NLP tools, and this is an attempt to improve the accuracy of Punjabi in the English NMT system by using named entities and MWEs in the corpus. The developed NMT models were assessed using human evaluation through adequacy and fluency as well as automated assessment tools such as the bilingual evaluation study (BLEU) and translation error rate (TER) score. Results show that using word embedding (WE) and MWEs corpus increased the accuracy of translation for the Punjabi to English language pair. The best BLEU score obtained was 15.45 for the small test set, 43.32 for the medium test set, and 34.5 for the large test set, respectively. The best TER rate score obtained was 57.34% for the small test set, 37.29% for the medium test set, and 53.79% for the large test set, repectively.

No abstract